© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84632
    Prev
    Next
    INDEX
    Explanations

    phrases or clauses that begin with "As" to indicate a relationship or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etter
    -0.07
     evidenced
    -0.07
    .ua
    -0.06
    plementation
    -0.06
    Getty
    -0.06
    ?$
    -0.06
     denen
    -0.06
    152
    -0.06
    stm
    -0.06
    activ
    -0.06
    POSITIVE LOGITS
    unga
    0.09
    omi
    0.07
    IDGET
    0.07
    ROUGH
    0.07
     Graf
    0.07
    rana
    0.07
    elow
    0.07
     Trades
    0.07
     ÑĤÑĢа
    0.07
     no
    0.06
    Activations Density 0.028%

    No Known Activations